Machine learning algorithm-based estimation model for the severity of depression assessed using Montgomery-Asberg depression rating scale.

AIM: Depressive disorder is often evaluated using established rating scales. However, consistent data collection with these scales requires trained professionals. In the present study, the "rater & estimation-system" reliability was assessed between consensus evaluation by trained psychiatrists and the estimation by 2 models of the AI-MADRS (Montgomery-Asberg Depression Rating Scale) estimation system, a machine learning algorithm-based model developed to assess the severity of depression. METHODS: During interviews with trained psychiatrists and the AI-MADRS estimation system, patients responded orally to machine-generated voice prompts from the AI-MADRS structured interview questions. The severity scores estimated from two models of the AI-MADRS estimation system, the max estimation model and the average estimation model, were compared with those by trained psychiatrists. RESULTS: A total of 51 evaluation interviews conducted on 30 patients were analyzed. Pearson's correlation coefficient with the scores evaluated by trained psychiatrists was 0.76 (95% confidence interval 0.62-0.86) for the max estimation model, and 0.86 (0.76-0.92) for the average estimation model. The ANOVA ICC rater & estimation-system reliability with the evaluation scores by trained psychiatrists was 0.51 (-0.09 to 0.79) for the max estimation model, and 0.75 (0.55-0.86) for the average estimation model. CONCLUSION: The average estimation model of AI-MADRS demonstrated substantially acceptable rater & estimation-system reliability with trained psychiatrists. Accumulating a broader training dataset and the refinement of AI-MADRS interviews are expected to improve the performance of AI-MADRS. Our findings suggest that AI technologies can significantly modernize and potentially revolutionize the realm of depression assessments.

Involvement of cerebellar and subcortical connector hubs in schizophrenia.

BACKGROUND: Schizophrenia is considered a brain connectivity disorder in which functional integration within the brain fails. Central to the brain's integrative function are connector hubs, brain regions characterized by strong connections with multiple networks. Given their critical role in functional integration, we hypothesized that connector hubs, including those located in the cerebellum and subcortical regions, are severely impaired in patients with schizophrenia. METHODS: We identified brain voxels with significant connectivity alterations in patients with schizophrenia (n = 76; men = 43) compared to healthy controls (n = 80; men = 43) across multiple large-scale resting state networks (RSNs) using a network metric called functional connectivity overlap ratio (FCOR). From these voxels, candidate connector hubs were identified and verified using seed-based connectivity analysis. RESULTS: We found that most networks exhibited connectivity alterations in the patient group. Specifically, connectivity with the basal ganglia and high visual networks was severely affected over widespread brain areas in patients, affecting subcortical and cerebellar regions and the regions involved in visual and sensorimotor processing. Furthermore, we identified critical connector hubs in the cerebellum, midbrain, thalamus, insula, and calcarine with connectivity to multiple RSNs affected in the patients. FCOR values of these regions were also associated with clinical data and could classify patient and control groups with > 80 % accuracy. CONCLUSIONS: These findings highlight the critical role of connector hubs, particularly those in the cerebellum and subcortical regions, in the pathophysiology of schizophrenia and the potential role of FCOR as a clinical biomarker for the disorder.